Tooluck logoTooluck
SKILL.md

00-academic-router

Agent skill fromagentscope-ai/OpenJudge

Use when the user wants help with academic papers or citations but it's unclear which specific workflow fits — reviewing a paper, checking a BibTeX file for fake references, or benchmarking multiple LLMs on reference-recommendation accuracy. Also use when the user mentions paper review, peer review, BibTeX verification, citation checking, reference hallucination, or academic literature accuracy and hasn't specified which of those three tasks they mean. This skill is the entry router for the academic-eval suite: it asks one diagnostic question then routes to the right sub-skill.

How to install 00-academic-router

install 00-academic-router
# install the OpenJudge pack with the skills CLI
npx skills add agentscope-ai/OpenJudge

# or add only this skill to Claude Code: copy the folder

skills/academic-eval/00-academic-router/

# into

~/.claude/skills/00-academic-router/ (all projects)

.claude/skills/00-academic-router/ (one project)

skills/academic-eval/00-academic-router/SKILL.md

Apache-2.0Full file
1# Academic Eval Router
2
3Entry router for the `academic-eval` suite. You diagnose what the user actually
4wants and route them to one of three sub-skills. You don't review papers, verify
5BibTeX files, or run arena benchmarks yourself — you're the triage desk.
6
7Each sub-skill is self-contained: it carries inline everything it needs, so it can
8be installed and used on its own.
9
10## Diagnostic Question
11
12Ask (unless the user's request already makes the answer obvious):
13
14```
15To route you correctly, which of these matches what you want?
16
17a) Review a single paper (PDF or LaTeX source) for correctness/quality/novelty
18 — optionally also check its bibliography
19b) Check a standalone .bib file for fabricated or mismatched references
20 (no paper review needed)
21c) Benchmark/compare multiple LLMs on how often they hallucinate references
22 when asked to recommend citations (arena-style, many queries)
23```
24
25**Shortcut rule**: if the user already said "review my paper", "check this PDF",
26"verify this .bib file", or "compare models on reference hallucination", skip the
27question — the routing is already clear from their phrasing.
28
29## Triage Table
30
31| User says / has | Use workflow | What it does |
32|---|---|---|
33| "Review this paper" (PDF or `.tar.gz`/`.zip` TeX source) | `01-paper-review` | Multi-stage review: safety, correctness, quality/novelty score, criticality — optionally + BibTeX check |
34…

Excerpt shown under the repository's Apache-2.0 license.

More skills in OpenJudge

Keep exploring

Similar skill repositories

thedotmack /

claude-mem
116k

Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More

CCCXGHGM+135 skills

Newsletter

Join the Community

Subscribe to our newsletter for the latest news and updates